(109d) Developing computational techniques to accelerate/automate interpretation of soft materials’ structural characterization results microscopy and small angle scattering

My research group’s expertise lies in development of physics-based molecular models and simulation methods as well as data-driven machine learning models for designing and characterizing soft macromolecular materials. In this talk, I will highlight examples from my group’s recent work to showcase how we develop and use data-driven computational tools - CREASE [e.g., 1-3], PairVAE [4] to interpret experimental characterization data from small angle scattering and microscopy. I list below relevant recent publications from my group (# equal contributions, * corresponding author) on the topics I will cover in this talk.

1. Christian M. Heil, Anvay Patil, Ali Dhinojwala, and Arthi Jayaraman* Computational Reverse-Engineering Analysis for Scattering Experiments (CREASE) with Machine Learning Enhancement to Determine Structure of Nanoparticle Mixtures and Solutions, ACS Central Science (2022), 8, 7, 996-1007
2. M. Heil, Y. Ma, Bhuvanesh Bharti, Arthi Jayaraman*, Computational Reverse-Engineering Analysis for Scattering Experiments for Form Factor and Structure Factor Determination ('P(q) and S(q) CREASE'), JACS Au (2023) 3, 3, 889–904
3. M. Heil, A. Patil, B. Vanthournout, S. Singla, M. Bleuel, J-J. Song, Z. Hu, N. Gianneschi, M. Shawkey, S. Sinha, A. Dhinojwala*, A. Jayaraman*, Mechanism of Structural Colors in Binary Mixtures of Colloidal Nanoparticle-based Supraballs, Science Advances (2023) 9, 21, 10.1126/sciadv.adf2859
4. Lu and A. Jayaraman*, Pair-Variational Autoencoders (PairVAE) for Linking and Cross-Reconstruction of Characterization Data from Complementary Structural Characterization Techniques, JACS Au (2023) in press

Relevant open-source codes from my group are below

CREASE: https://crease-ga.readthedocs.io/en/latest/ and https://github.com/arthijayaraman-lab/crease_ga

PairVAE: https://github.com/arthijayaraman-lab/PairVAE